Geekbench AI Score

15312
Single Precision Score
17322
Half Precision Score
15329
Quantized Score
Geekbench AI 1.2.0 for macOS AArch64

Result Information

User BennyDaBall
Upload Date February 21 2025 04:02 AM
Views 2

System Information

AI Information
Framework Core ML
Backend GPU
Device Apple M4 Pro
System Information
Operating System macOS 15.3.1 (Build 24D70)
Model Mac mini (2024)
Model IDMac16,11
Motherboard Mac16,11
CPU Information
Name Apple M4 Pro
Topology 1 Processor, 14 Cores
Identifier Apple M4 Pro
Base Frequency 4.51 GHz
Cluster 110 Cores
Cluster 24 Cores
Memory Information
Size 48.00 GB

AI Performance

Workload Accuracy Score
Image Classification (SP)
100% 7530
1.40 KIPS
 
Image Classification (HP)
100% 8249
1.53 KIPS
 
Image Classification (Q)
97% 6809
1.27 KIPS
 
Image Segmentation (SP)
100% 11959
193.9 IPS
 
Image Segmentation (HP)
100% 12951
209.9 IPS
 
Image Segmentation (Q)
99% 13239
214.6 IPS
 
Pose Estimation (SP)
100% 56584
66.0 IPS
 
Pose Estimation (HP)
100% 59015
68.9 IPS
 
Pose Estimation (Q)
95% 55848
65.5 IPS
 
Object Detection (SP)
100% 7088
562.3 IPS
 
Object Detection (HP)
100% 7671
608.4 IPS
 
Object Detection (Q)
91% 6356
507.9 IPS
 
Face Detection (SP)
100% 25534
303.4 IPS
 
Face Detection (HP)
100% 28080
333.6 IPS
 
Face Detection (Q)
100% 21035
249.9 IPS
 
Depth Estimation (SP)
100% 33133
255.3 IPS
 
Depth Estimation (HP)
99% 36184
278.8 IPS
 
Depth Estimation (Q)
85% 29372
229.6 IPS
 
Style Transfer (SP)
100% 123535
158.8 IPS
 
Style Transfer (HP)
100% 135691
174.4 IPS
 
Style Transfer (Q)
96% 126960
163.8 IPS
 
Image Super-Resolution (SP)
100% 22887
845.1 IPS
 
Image Super-Resolution (HP)
100% 24323
898.1 IPS
 
Image Super-Resolution (Q)
99% 19262
711.2 IPS
 
Text Classification (SP)
100% 2917
3.89 KIPS
 
Text Classification (HP)
100% 5136
6.85 KIPS
 
Text Classification (Q)
93% 5095
6.84 KIPS
 
Machine Translation (SP)
100% 2813
48.5 IPS
 
Machine Translation (HP)
100% 2921
50.3 IPS
 
Machine Translation (Q)
98% 2909
50.3 IPS
 

Compare

Set Baseline Geekbench 6 now available